Semantic search (RAG) in Invercargill.
Semantic search (RAG) designed around the way an Invercargill team actually runs.
From Tiwai Point to the dairy sheds, Southland businesses run lean crews. We automate rosters, reporting and invoicing so fewer hours go to the office.
Knows the New Zealand rules.
Ask questions across your manuals, contracts and records and get answers with the source attached, not a guess.
- An annual return every year
- Holidays Act until August 2028
- Data that stays in New Zealand
From one-person trades to national organisations, we find the hours :)
The questions a public sector buyer asks, answered up front: privacy impact, the NZISM, where the data lives and how an algorithm is held to account.
*Illustrative example based on nine hours a week of admin. Actual results vary by workflow and business.
We'd call the engagement a success when Invercargill teams are using the system without thinking about us. Average search time drops from 6 minutes to 12 seconds. Kiwi Dynamics
How it works in Invercargill
We find the one workflow costing Invercargill businesses the most hours, ship a working slice into production in weeks, prove it pays for itself, then harden it and hand it over.
Not your typical AI agency.
*Every engagement is scoped and quoted up front. Results vary by workflow and business.
Invercargill, up close.
Southland's economy rests on agriculture and processing, and the New Zealand Aluminium Smelter at Tiwai Point, across the harbour from Bluff, is the country's only aluminium smelter.
Tiwai Point has secured its energy supply to at least 2044. Most New Zealand dairy herds calve in spring, July to September.
Straight answers
What happens if we want to swap a vendor out later?
Semantic search (RAG) is built behind a small adapter layer specifically so swapping a model provider or a data source is a one-day job, not a re-architecture. Pinecone, Claude, Postgres pgvector, Vercel AI SDK are our defaults, but the build is intentionally portable.
What does semantic search (RAG) cost for an Invercargill?
Pilots start from a fixed scope priced to land a measurable result inside 6 weeks. Pricing depends on data volume, integration complexity, and whether you need us on managed services afterwards. We'll quote precisely after a 30-minute scoping call.
What's the realistic timeline for semantic search (RAG) with an Invercargill?
Most Invercargill businesses have their first usable slice in week 5 or 6. We'd rather ship narrow and real than broad and aspirational - your team gets to use the thing well before the engagement is "done".
How does this fit the Public Service AI Framework?
The framework, led by the Government Chief Digital Officer, asks for safe, transparent and accountable AI. Agencies that sign the Algorithm Charter also commit to transparency in how they use algorithms.
Do you respond to government tenders?
Most large government contracts are advertised on GETS, the Government Electronic Tender Service, where suppliers register with RealMe.
Talk to us about semantic search (RAG)
StartContact us
Tell us what you're trying to do and we'll reply with how we'd build it, no obligation.
Was this helpful?
Thanks, your comment is with our team.